2nd International Conference on Machine Learning and Computer Science(IMLCS'2013) August 25-26, 2013 Kuala Lumpur (Malaysia)
A Unified Intrusion Alert System using Motion
Detection and Face Recognition
Sameerchand Pudaruth, Faugoo Indiwarsingh and Nandrakant Bhugun
AbstractProvision of home security services has become an
integral part of our lives in todays technological society where
attackers usually have all the necessary means and resources at their
disposal. In light of this problem, we have developed a unified
intruder alert system by integrating motion detection with face
recognition. The motion detection module is responsible to determine
the level of activity while the face detection module differentiates
between authorised people and intruders. Several experiments were
conducted with live stream video from a camera and the results
obtained are very reliable. The system effectively distinguishes
between the property owners and other people and alarms are raised
when the motion level exceeds a threshold value. The capture image
is sent to the owners mailbox when such an alarm is raised which he
can view from his mobile device, anywhere and anytime. Our system
is better than many proposed systems as it combines both motion
detection and face recognition in a single system. The motion is also
categorised in different levels, each level representing a certain
degree of risk. In order not to annoy him with false alarms, he is
notified only the risk of intrusion is real.
KeywordsSecurity, Motion Detection, Face Recognition.
I. INTRODUCTION
A N automated home security system, just like a car, has
become one of our basic needs. Due to work constraints,
people are spending more and more time away from their
homes. Most homes are now equipped with state-of-the-art
technological devices like digital TVs, digital cameras or
camcorders, smart refrigerators, washing machines, etc. It is
also common knowledge that these are the favourite items of
burglars who finds in them a quick way of making a living.
Due to all these luxuries, we are able to have a modern
lifestyle. However, it is also incumbent on us to think about
the security of these assets and our family as well. Thus, along
with the modern way of living, security has a prime value. A
visual surveillance system, based on computer vision
technology, can be very helpful to achieve this objective. The
key to home security is constant monitoring.
CCTV (Closed-Circuit Television) cameras have proved to
be very useful for monitoring applications. The first CCTV
was installed by Siemens AG at Test Stand Vii in
Peenemunde, Germany in 1942 for observing the V-2 rockets
launching [1]. Since then the CCTV has been continuously
evolving from a simple passive surveillance system to a more
S. Pudaruth is with the University of Mauritius (phone: 230-403-7754; fax:
230-454-9642; e-mail: s.pudaruth@uom.ac.mu).
I. Faugoo is with the University of Mauritius.
N. Bhugun is with the University of Mauritius.
17
advanced and intelligent monitoring system. It can now be
considered as an integral part of our society.
CCTVs have become ubiquitous in their surveillance tasks
and are efficiently performing monitoring of areas to ensure
the security of the public. In the UK alone, it is estimated that
there are about 4.2 million CCTV cameras for a population of
62.2 million [2]. They have successfully been used in many
places such as for traffic monitoring, maintaining law and
order, monitoring of chemical processes in production control
in various types of industries, etc. They are also very common
in shops, department stores [3], supermarkets, hypermarkets
and shopping malls where they have successfully been used to
detect suspicious behaviour, shop lifting and robberies. They
have also proved to be very useful in places where there are
huge crowds such as in stadiums.
The main objective of this work is the setting up of an
intelligent visual surveillance home security system through
the use of computer vision techniques. Computer vision is the
ability to make machines see through the application of
science and technology. Human beings are able to perceive the
three-dimensional structure of the world surrounding them
without any difficulty [4], but machines do not have these
capabilities, unless provided. The system uses motion
detection coupled with face recognition to recognise intruders.
Motion detection or activity detection is the process
whereby a surveillance system has the capability to detect and
capture an event in the cameras field of view and upon the
event, take required actions, such as record video or sound an
alarm. In motion detection, sequential images are compared to
detect differences between them resulting in motion detection
based on the percentage difference between these images. An
interesting issue regarding visual surveillance systems is its
legality. The law is different for each jurisdiction. According
to the Data Protection Act 2004 [5] in force in Mauritius, a
data controller cannot collect personal data unless it is
collected for a lawful purpose with an activity associated with
the data controller. The data controller must also prove that the
collection of this data is relevant and necessary for that
activity. Thus, the permission of the Data Commissioner must
be obtained if individuals wish to install surveillance cameras
as their place of residence if the cameras field of view is
outside the boundary their own yard [6]. Furthermore, upon
installation of the surveillance system, a notice board should
be displayed outside the house, to inform people that the house
is under camera surveillance and they will be monitored if
they enter the property.
 2nd International Conference on Machine Learning and Computer Science(IMLCS'2013) August 25-26, 2013 Kuala Lumpur (Malaysia)

II. RELATED WORKS recognition to eliminate false alerts and motion levels are not
The rise in popularity of surveillance systems has been categorised. Mahalakshmi et al. [2] proposed an architecture
fuelled by the availability of cheap cameras and the ever for the setting up of a visual surveillance system using CCTV
increasing processing capacity of CPUs. Indeed, significant cameras. They also provided considerable technical details
research work has been done in this field during the past two about the equipment required and how to install and to use
decades. The following is a brief review of some previous them. Unfortunately, the system has not yet been tested and
works about visual surveillance systems. Yuan et al. [7] therefore results have yet to be provided. Rani [14] used an
proposed a distributed visual surveillance system by active infrared motion detector to detect motion in a home
connecting the output from multiple cameras to a local area environment. If the path between the radiation source and the
network. They used a simple background subtraction method sensor is interrupted, motion is assumed and this is linked to
to detect pedestrians and vehicles. However, their system the activity of an intruder.
could not recognise vehicles or pedestrians, it could only
detect their presence. The system was tested under controlled III. DESIGN AND IMPLEMENTATION
conditions which gave a detection accuracy of more than 95%.
However, the authors conceded that the system will perform
poorly under when it is raining, when there is little contrast
between the objects of interest and the background or when
there are many vehicles moving close to each other.
Lee et al. [8] developed a real-time threat assessment
system which could effectively distinguish between people,
animals and vehicles but cannot recognise them. They used
the contours of shapes obtained from each frame and
compared it with that in their database in order to differentiate
between people, animals and vehicles. An interesting work
was done by See and Lee [9] in which they proposed to have a
multi-modal home security system. They used a face
recognition module to authenticate the user and a motion
detection module to detect movement. However, the outputs
from these two systems were evaluated separately and were
not integrated into a single system to detect intruders.
Ansari et al. [10] described and implemented a sophisticated
motion detection system using Matlab to detect motion from a
video stream. The video is stored only when motion is
detected. However, they do not have different levels of motion
and owners are not given any warning messages. Nebel et al.
[11] reviewed some of the state-of-the-art approaches for
recognising human action from surveillance videos. They
showed that even the best performing systems could only
recognise a few distinct and basic actions with an accuracy of
only 70% under controlled conditions. Thus, they argue that
computer vision systems have not matured enough to be useful
in human action recognition. Kosba et al. [12] designed and
implemented a passive motion detection system which uses
the signal strength and waveform of wi-fi signals to detect
motion instead of relying on visual systems. They argue that
their system is better as it is not limited to line-of-sight vision Fig. 1 Algorithm to detect motion and recognise intruder
and it works even in the presence of smoke and at night. Their
current system gives a detection accuracy of 93%. However, Fig. 1 shows how the system operates. In the monitoring
changes in the physical layout of the building and interference mode, the camera monitors a specified area from an angle at a
from other devices can have an impact of their accuracy. They resolution of 640 x 480. In motion level exceeds a threshold
are also investigating the effect of size, shape and motion value of 15%, this triggers the face detection module. The
pattern on the performance of their system. motion level is calculated by taking the difference between the
Tuscano et al. [13] implemented a simple but effective current frame and the previous frame. If a person is detected,
surveillance system which upon detection of motion sounds an the face recognition algorithm tries to track and recognise the
alarm, start video recording, sends an email and send an MMS face by comparing it to the database of stored images. The
to the mobile phone of the security officer in charge of the face recognition module uses the Eigen face recognition
building. However, the system does not perform face algorithm to recognise and track faces. If that persons face is

18
 2nd International Conference on Machine Learning and Computer Science(IMLCS'2013) August 25-26, 2013 Kuala Lumpur (Malaysia)
not present in the database, an alert is given which is then sent
to the owner mailbox.
IV. EVALUATION OF RESULTS
The system was tested in different light conditions. Motion
capture in normal daylight conditions is more responsive than
night motion capture. This limitation is due to the fact that the
Infra-Red (IR) camera captures only one frame per second in a
dark room while the in daylight it captures thirty frames per
second. Nevertheless, the system is able to detect motion
under both conditions. Thirteen different persons were asked
to walk in front of the camera, one at a time. All of them were
detected. However, the recognition rate was between only
62%. Furthermore, recognition works only up to a distance of
7m. For detection, the moving object/person can be up 12m.
The system is designed to capture 30 frames per second (fps).
If fewer frames are captured per second, some part of the
action in the event may be missed. 30fps is sufficient and
allow selection of useful frames to be retrieved and analysed.
These frames are also used to build the video, for streaming
purposes. A emailing system was tested when the owner is at a
remote place and he receives an intruder alert on his mobile
phone via the internet. However, a fast internet connection of
at least 256 Mbps is required to have a quick response. For the
system to operate in real-time, images are at a resolution of
640 x 480 pixels. This allows for fast processing at 30fps.
Small file size also allows for faster uploads and downloads.
Fig. 2 Difference images showing motion
Fig. 2 shows the instant when a person enters the field of
view and the system start to detect him from the starting point,
i.e., from a distance of 12 metres. This can be seen as some
dots from the first frame, indicating motion, then as the person
come closer to the camera, the persons figure and outlines
becomes more prominent. When the person comes within 7m,
the face recognition module will try to recognise the moving
object. If the face is recognised, no action is necessary.
However, if the face is not recognised the system will capture
19
the frames and sends them to the email address specified by
the owner of the house.
Visual surveillance systems have many advantages. Firstly,
they are not obstructive. Secondly, authentication and tracking
can be done automatically from a distance. Thirdly, the setup
requires simple low-cost cameras and a computer. Sensor-
based systems, in contrast, usually rely on some sort of contact
to detect movement. Furthermore, many surveillance
applications depend on one feature only whereas this system
uses two features which make it even more robust, reliable and
effective. The proposed system can easily be implemented by
anyone wishing to protect their home and its assets.
V. CONCLUSION
The aim of this research was to develop an integrated
intruder system by combining motion detection with face
recognition. The motion detector uses background subtraction
to estimate the motion and then associates it with a certain risk
level. The face recognition distinguishes between authorized
persons and intruders in order to eliminate false alerts. The
system has been tested in real-life scenarios and this low-cost
home surveillance system shows good performance both
during the day and at night when infra-red cameras were used.
The owner receives an email with the captured frame as
attachment when a high risk alert is raised. The system can be
improved by adding more cameras so that one is present in
each room. However, additional work is required for the face
recognition module to increase its recognition ratio and to
make it less sensitive to variations in light intensity. .
REFERENCES
[1] Lockpick Library. 2011. Security Camera System. [ONLINE] Available
at:http://www.lockpicklibrary.com/cameras. [Accessed 2 May 13].
[2] Mahalakshmi R., Manjula M., Saranya S., Vaishnavi P., Shalini J. and
Arasa Kumar R. (2013). Intrusion Detection by Facial Recognition using
CCTV Cameras with Video Management System. International Journal
of Advanced Electrical and Electronics Engineering. 2(2), pp. 59-62.
[Accessed 2 May 13]
[3] Brodsky T., Cohen R., Cohen-Solal E., Gutta S., Lyons D., Philomin V.,
and Trajkovic M.: Visual Surveillance in retail stores and in the home,
in: Advanced Video-based Surveillance Systems (Kluwer Academic
Publishers, Boston, 2001), Chapter 4, pp. 50-61. [Accessed 2 May 13]
[4] Richard Szeliski, 2011. Computer Vision: Algorithms and Applications
(Texts in Computer Science). 1st ed. -: Springer.
[5] The Data Protection Act 2004 . [ONLINE] Available
at:http://www.gov.mu/portal/sites/ncbnew/files/DPA.pdf. [Accessed 24
May 2013].
[6] The Powers of Commissioner. [ONLINE] Available at:http://
dataprotection.gov.mu/English/AboutUs/The%20Commissioner/Pages/T
he-Powers-of-the-Commissioner-.aspx. [Accessed 24 May 2013].
[7] X. Yuan , Z. Sun, Y. Varol and G. Bebis (2003). A distributed Visual
Surveillance System, IEEE International Conference on Advanced
Video and Signal Based Surveillance, Miami, July 2003.
[8] D.J. Lee, P. Zhan, A. Thomas, R. Schoenberger (2004). Shape-based
Human Intrusion Detection, SPIE International Symposium on Defense
and Security, Visual Information Processing XIII, vol. 5438, pp. 81-91,
Orlando, Florida, USA, April 12-16, 2004.
[9] John See, Sze-Wei Lee (2007). An integrated vision-based architecture
for home security system. IEEE Trans. Consumer Electronics, 53(2), pp.
489-498.
[10] Asif Ansari, T.C.Manjunath, C.Andril (2008) Implementation of a
Motion Detection System, IEEE International Journal of Electrical and
Computer Computer Engineering, 3(1), pp. 52-63.
 2nd International Conference on Machine Learning and Computer Science(IMLCS'2013) August 25-26, 2013 Kuala Lumpur (Malaysia)

[11] J.C. Nebel, M Lewandowski, J Thevenon, F Martinez, S.A. Velastin

(2011). Are Current Monocular Computer Vision Systems for Human
Action Recognition Suitable for Visual Surveillance Applications?, 8th
International Conference on Information Visualisation, LNCS 6938,
Springer, Sept 26-28, Las Vegas, USA, pp. 290-299.
[12] A.E. Kosba, A. Saeed and M. Youssef, RASID (2012). A Robust
WLAN Device-free Passive Motion Detection System, the Tenth Annual
IEEE International Conference on Pervasive Computing and
Communication (Per-Com 12), March 2012.
[13] Tuscano C., Lopes B., Machado S. (2013). Smart Web Cam Motion
Detection Surveillance System. International Journal of Modern
Engineering Research, 3(2), pp. 1169-1171.
[14] Abd. Rani , Mior Mohammad Hafiizh (2007). Active infrared motion
detector for house security system. Eng D thesis, University Malaysia
Pahang.

20